Benchmark menu

Per-game leaderboard

GB2-05: Hex

This page compares player programs for GB2-05: Hex in the balanced filter. Programs are ranked by their relative score within this game.

GB2-05: Hex

Hex

Hex is a connection game on a hexagonal grid where players race to join opposite board edges, with a swap option after the first move.

Scores here compare player programs using DuelLab's encoded rules for Hex; they are not a broad measure of human play strength.

GB2-05: Hex by model and setting

Player programs are ranked by relative per-game score (0–100). Raw rating is shown as an advanced metric, alongside wins, draws, losses, and a per-game uncertainty index.

Reasoning level: Balanced Game: GB2-05: Hex
GB2-05: Hex - Balanced filter
Rank Model Score Contributing programs Raw Elo W / D / L Uncertainty
1Claude Opus 586.321911.2164 / 0 / 227.8
2GPT-5.481.211852.979 / 0 / 177.0
3GPT-5.6 Sol78.111818.977 / 0 / 177.5
4Gemini 3.6 Flash75.021774.5231 / 0 / 770.0
5GPT-5.569.311723.354 / 0 / 2611.8
6Grok Build 0.168.011702.558 / 0 / 465.0
7Grok 4.564.611664.465 / 0 / 375.5
8Claude Fable 563.811658.455 / 0 / 358.7
9Qwen3.7 Plus61.311625.059 / 0 / 572.5
10GPT 561.311631.245 / 0 / 3910.5
11GPT-5.6 Terra60.611620.858 / 0 / 406.5
12Gemma 4 31B59.511605.462 / 0 / 522.9
13Kimi K2.7 Code59.211604.152 / 0 / 466.5
14Claude Opus 4.857.411581.562 / 0 / 483.7
15Claude Opus 4.557.211570.3108 / 0 / 840.0
16Gemini 3.5 Flash57.011578.755 / 0 / 475.5
17O356.811575.661 / 0 / 435.0
18GLM-5.256.611582.236 / 0 / 3415.6
19GPT-5.4 Mini56.411570.566 / 0 / 463.3
20Kimi K355.811556.3103 / 0 / 670.0
21Qwen3.7 Max55.711562.359 / 0 / 533.3
22Muse Spark 1.255.611564.953 / 0 / 417.5
23GPT-5.4 Nano53.421540.597 / 0 / 839.1
24Qwen3.8 Max52.911580.912 / 0 / 865.4
25Step 3.7 Flash51.511515.750 / 0 / 564.6
26North Mini Code50.421519.064 / 0 / 5024.2
27Claude Sonnet 549.111492.148 / 0 / 448.1
28GPT-5.6 Luna48.211481.644 / 0 / 497.8
29GPT-OSS 120B46.611461.047 / 0 / 594.6
30LongCat 2.044.521428.5149 / 0 / 1850.0
31MiMo-V2.544.221433.198 / 0 / 1223.8
32Ox Alpha38.431426.714 / 0 / 3477.5
33Laguna S 2.134.521315.1122 / 0 / 2430.0
34Inkling Small33.011365.44 / 0 / 1277.5
35MiMo-V2.5-Pro32.511302.535 / 0 / 656.0
36Nex N2 Pro32.311301.130 / 0 / 647.5
37DeepSeek V4 Flash31.121292.461 / 0 / 8913.6
38Inkling28.911258.241 / 0 / 772.1
39Gemini 3.1 Flash Lite23.811207.226 / 0 / 629.2
40Gemini 3.5 Flash Lite17.921129.367 / 0 / 2530.0
41Minimax M30.01936.02 / 0 / 947.0

Individual player programs

Each row is one accepted player program for GB2-05: Hex. A model can appear more than once when it produced more than one program. Score is the normalized 0–100 result; Elo and W / D / L show the underlying play record. Confidence and evidence can be blank when too few compatible matches are available. Draws at the move limit count; one-sided model faults are listed separately.

Showing 52 player programs.
Player IDModelStatusScoreEloConfidenceW / D / LRated / attemptedOpponentsCapped drawsFaults / playersGeneration
E-ad7cf41c05ec3f64Claude Fable 5Rated63.8165855 / 0 / 3590 / 904500 / 1First try · 2026-07-02
E-a75e9d71efa4a6bcClaude Opus 4.5Rated57.21570108 / 0 / 84192 / 1927100 / 1First try · 2026-07-21
E-ff0722d17402bafaClaude Opus 4.5Waiting0 / 0 / 00 / 0000 / 1First try · 2026-07-02
E-924d7e6ee41b562eClaude Opus 4.8Rated57.4158262 / 0 / 48110 / 1105300 / 1First try · 2026-07-02
E-32c377b229530444Claude Opus 5Rated81.7185978 / 0 / 1694 / 944700 / 1First try · 2026-07-25
E-d7111b534ebcaba2Claude Opus 5Rated90.8196386 / 0 / 692 / 924600 / 1First try · 2026-07-25
E-77d8a88f79b44f7dClaude Sonnet 5Rated49.1149248 / 0 / 4492 / 924400 / 1First try · 2026-08-09
E-a0518a43c688d1e2North Mini CodeRated53.2154240 / 0 / 3474 / 743700 / 1First try · 2026-07-02
E-06a41d0e11b18b77DeepSeek V4 FlashRated33.5132028 / 0 / 4674 / 743700 / 1First try · 2026-07-01
E-2c1cbd253f3a9d69DeepSeek V4 FlashRated28.7126533 / 0 / 4376 / 763800 / 1First try · 2026-07-02
E-7603462aff103041Gemini 3.1 Flash LiteRated23.8120726 / 0 / 6288 / 884400 / 1Repaired · 2026-07-02
E-a7ce764239377b3fGemini 3.5 FlashRated57.0157955 / 0 / 47102 / 1025100 / 1Repaired · 2026-07-02
E-3dd83d6fa9f8f758Gemini 3.5 Flash LiteRated17.0111931 / 0 / 127158 / 1585900 / 1First try · 2026-07-24
E-8826ab29e7591eceGemini 3.5 Flash LiteRated18.8113936 / 0 / 126162 / 1626100 / 1First try · 2026-07-24
E-5bcc61f900210bfaGemini 3.6 FlashRated97.32027147 / 0 / 7154 / 1546200 / 1First try · 2026-07-24
E-d95a1da824d70f6dGemini 3.6 FlashRated52.6152284 / 0 / 70154 / 1546200 / 1First try · 2026-07-24
E-fd1bc1e2e6ac48fbGemma 4 31BRated59.5160562 / 0 / 52114 / 1145200 / 1Repaired · 2026-07-02
E-9e5b308c41a36374GPT 5Rated61.3163145 / 0 / 3984 / 844200 / 1First try · 2026-07-02
E-34e3865fc087a754GPT-5.4Rated81.2185379 / 0 / 1796 / 964400 / 1First try · 2026-08-09
E-0791f6b66243ec1aGPT-5.4 MiniRated56.4157066 / 0 / 46112 / 1125200 / 1First try · 2026-07-02
E-8e40431df091d53fGPT-5.4 NanoRated76.8180963 / 0 / 1376 / 763800 / 1First try · 2026-07-02
E-a0d8c8fd6b01598cGPT-5.4 NanoRated29.9127234 / 0 / 70104 / 1045100 / 1First try · 2026-07-09
E-ffa82d1e96e897abGPT-5.5Rated69.3172354 / 0 / 2680 / 804000 / 1First try · 2026-07-02
E-8056d7cf3d4b6248GPT-5.6 LunaRated48.2148244 / 0 / 4993 / 934400 / 1First try · 2026-08-09
E-c9acd4a3fb993f97GPT-5.6 SolRated78.1181977 / 0 / 1794 / 944400 / 1First try · 2026-08-09
E-9664e98d37ece097GPT-5.6 TerraRated60.6162158 / 0 / 4098 / 984600 / 1First try · 2026-07-10
E-73a7ad076eeaa6aeLongCat 2.0Rated66.31675110 / 0 / 58168 / 1686000 / 1First try · 2026-07-24
E-8b7eb63d4f53d846LongCat 2.0Rated22.6118239 / 0 / 127166 / 1666100 / 1First try · 2026-07-24
E-782ab5805e8c7fe1Muse Spark 1.2Rated55.6156553 / 0 / 4194 / 944400 / 1First try · 2026-08-13
E-fb8ac45946e32e22Minimax M3Rated0.09362 / 0 / 9496 / 964700 / 1Repaired · 2026-07-02
E-952fba19b28982d5Kimi K2.7 CodeRated59.2160452 / 0 / 4698 / 984800 / 1Repaired · 2026-07-02
E-895556dde47644aeKimi K3Rated55.81556103 / 0 / 67170 / 1705900 / 1First try · 2026-07-24
E-5f76f577111bee8dNex N2 ProRated32.3130130 / 0 / 6494 / 944600 / 1Repaired · 2026-07-02
E-343b92f3dda3dcb5O3Rated56.8157661 / 0 / 43104 / 1045100 / 1First try · 2026-07-02
E-5ef540286ecbb63dGPT-OSS 120BRated46.6146147 / 0 / 59106 / 1065100 / 1Repaired · 2026-07-02
E-53ce0020411c86d4Laguna S 2.1Rated20.2115438 / 0 / 134172 / 1726500 / 1First try · 2026-07-24
E-62e15a037ee860c1Laguna S 2.1Rated48.9147684 / 0 / 109193 / 1936800 / 1Repaired · 2026-07-24
E-435ec29661cdc285Qwen3.7 MaxRated55.7156259 / 0 / 53112 / 1125300 / 1Repaired · 2026-07-02
E-6cc7454f585005c4Qwen3.7 PlusRated61.3162559 / 0 / 57116 / 1165400 / 1Repaired · 2026-07-02
E-2dec08c905be48b9Qwen3.8 MaxLimited data52.9158112 / 0 / 820 / 201100 / 1First try · 2026-08-08
E-149dc099de9a50cdOx AlphaRated40.514506 / 0 / 1016 / 16800 / 1First try · 2026-08-22
E-6f88d9900795b3a1Ox AlphaRated28.813180 / 0 / 1616 / 16800 / 1First try · 2026-08-22
E-71c7a6b241c3e968Ox AlphaRated46.015138 / 0 / 816 / 16800 / 1First try · 2026-08-22
E-7b9b33921ba865f5Step 3.7 FlashRated51.5151650 / 0 / 56106 / 1065200 / 1Repaired · 2026-07-02
E-ae60ed096a69eeffInklingRated28.9125841 / 0 / 77118 / 1185900 / 1Repaired · 2026-07-24
E-cb36e2fcb99cfafdInkling SmallLimited data33.013654 / 0 / 1216 / 16800 / 1First try · 2026-08-09
E-824ec3caceabd338Grok 4.5Rated64.6166465 / 0 / 37102 / 1025100 / 1First try · 2026-07-24
E-4aac1b6621aeae38Grok Build 0.1Rated68.0170258 / 0 / 46104 / 1044800 / 1Repaired · 2026-07-02
E-ad48cf51fe7da3ccMiMo-V2.5Rated47.5146959 / 0 / 59118 / 1185800 / 1Repaired · 2026-07-02
E-faaa866ee28d6401MiMo-V2.5Rated41.0139839 / 0 / 63102 / 1025100 / 1Repaired · 2026-07-02
E-9c228ad72a159b33MiMo-V2.5-ProRated32.5130235 / 0 / 65100 / 1004800 / 1Repaired · 2026-07-02
E-3916ba303b2ff700GLM-5.2Rated56.6158236 / 0 / 3470 / 703500 / 1Repaired · 2026-07-11